A "liquid health check" from blood test could predict disease risk

A study partly funded by the NHLBI has shown that proteins in our blood could offer a comprehensive "liquid health check" by assessing our health and predicting our risk of developing a wide range of diseases. The findings, published in Nature Medicine, come from a proof-of-concept study based on five observational cohorts in almost 17,000 participants, researchers scanned 5,000 proteins in a plasma sample taken from each participant.

The researchers analyzed the results using statistical methods and machine learning techniques to develop predictive models that could, for instance, show that someone with a specific patter of proteins in her blood has a higher risk of developing diabetes.

The models, whose accuracy varied, covered many risk factors including levels of liver fat, kidney function and visceral fat, alcohol consumption, physical activity and smoking behavior, and for risk of developing type 2 diabetes and cardiovascular disease.